Show simple item record

Non-parametric approximate linear programming for MDPs

dc.contributor.advisor Parr, Ronald
dc.contributor.advisor Conitzer, Vincent
dc.contributor.advisor Maggioni, Mauro
dc.contributor.advisor Ferrari, Silvia
dc.contributor.author Pazis, Jason
dc.date.accessioned 2013-01-16T20:47:45Z
dc.date.issued 2012
dc.identifier.uri https://hdl.handle.net/10161/6189
dc.description.abstract One of the most difficult tasks in value function based methods for learning in Markov Decision Processes is finding an approximation architecture that is expressive enough to capture the important structure in the value function, while at the same time not overfitting the training samples. This thesis presents a novel Non-Parametric approach to Approximate Linear Programming (NP-ALP), which requires nothing more than a smoothness assumption on the value function. NP-ALP can make use of real-world, noisy sampled transitions rather than requiring samples from the full Bellman equation, while providing the first known max-norm, finite sample performance guarantees for ALP under mild assumptions. Additionally NP-ALP is amenable to problems with large (multidimensional) or even infinite (continuous) action spaces, and does not require a model to select actions using the resulting approximate solution.
dc.title Non-parametric approximate linear programming for MDPs
dc.type Master's thesis
dc.department Computer Science
pubs.organisational-group Duke
pubs.organisational-group Duke
pubs.organisational-group Trinity College of Arts & Sciences
pubs.organisational-group Duke
pubs.organisational-group Trinity College of Arts & Sciences
pubs.organisational-group Computer Science
pubs.publication-status Published


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record